# GPT-5-Codex vs Phi 3 Medium 4k Instruct

> GPT-5-Codex is the stronger model overall, scoring 37.3 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5-Codex leads 41.9 to 32.3.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5-Codex | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 37.3 | 32.4 |
| Rank | 190 | 246 |
| Context | 400K | — |
| Input $/M | $1.25 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5-Codex: 41.9 (#100)
- Phi 3 Medium 4k Instruct: 32.3 (#263)

| Benchmark | GPT-5-Codex | Phi 3 Medium 4k Instruct |
|---|---|---|
| WeirdML | 54.5% | — |
| LMArena Coding | — | 1130 |

## Agentic & Tool Use

- GPT-5-Codex: 30.8 (#66)
- Phi 3 Medium 4k Instruct: —

| Benchmark | GPT-5-Codex | Phi 3 Medium 4k Instruct |
|---|---|---|
| Terminal-Bench | 44.3% | — |

## Reasoning

- GPT-5-Codex: 30.0 (#80)
- Phi 3 Medium 4k Instruct: 20.8 (#214)

| Benchmark | GPT-5-Codex | Phi 3 Medium 4k Instruct |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| LMArena Hard Prompts | — | 1127 |

## Math

- GPT-5-Codex: —
- Phi 3 Medium 4k Instruct: 30.9 (#202)

| Benchmark | GPT-5-Codex | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | — | 1173 |

## Knowledge

- GPT-5-Codex: —
- Phi 3 Medium 4k Instruct: 29.6 (#226)

| Benchmark | GPT-5-Codex | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | — | 1108 |

## Multilingual

- GPT-5-Codex: —
- Phi 3 Medium 4k Instruct: 30.8 (#258)

| Benchmark | GPT-5-Codex | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | — | 1094 |
| LMArena Chinese | — | 1108 |
| LMArena French | — | 1109 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Russian | — | 1145 |
| LMArena Spanish | — | 1095 |

## Instruction Following

- GPT-5-Codex: —
- Phi 3 Medium 4k Instruct: 57.8 (#263)

| Benchmark | GPT-5-Codex | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1114 |

## Long Context

- GPT-5-Codex: —
- Phi 3 Medium 4k Instruct: 33.9 (#250)

| Benchmark | GPT-5-Codex | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1120 |

## Writing & Preference

- GPT-5-Codex: —
- Phi 3 Medium 4k Instruct: 34.3 (#267)

| Benchmark | GPT-5-Codex | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | — | 1138 |
| LMArena Creative Writing | — | 1106 |
| LMArena Multi-Turn | — | 1088 |

## FAQ

### Is GPT-5-Codex better than Phi 3 Medium 4k Instruct?

GPT-5-Codex is the stronger model overall, scoring 37.3 to 32.4 on the Noometry Index.

### Is GPT-5-Codex or Phi 3 Medium 4k Instruct better for coding?

GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 32.3 in the Noometry coding category.

### How many benchmarks do GPT-5-Codex and Phi 3 Medium 4k Instruct share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.